Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,451 @@
+---
+license: cc-by-nc-4.0
+language:
+- ro
+base_model: OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28
+datasets:
+- OpenLLM-Ro/ro_sft_alpaca
+- OpenLLM-Ro/ro_sft_alpaca_gpt4
+- OpenLLM-Ro/ro_sft_dolly
+- OpenLLM-Ro/ro_sft_selfinstruct_gpt4
+- OpenLLM-Ro/ro_sft_norobots
+- OpenLLM-Ro/ro_sft_orca
+- OpenLLM-Ro/ro_sft_camel
+tags:
+- llama-cpp
+- gguf-my-repo
+model-index:
+- name: OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: RoMT-Bench
+      type: RoMT-Bench
+    metrics:
+    - type: Score
+      value: 5.15
+      name: Score
+    - type: Score
+      value: 6.03
+      name: First turn
+    - type: Score
+      value: 4.28
+      name: Second turn
+  - task:
+      type: text-generation
+    dataset:
+      name: RoCulturaBench
+      type: RoCulturaBench
+    metrics:
+    - type: Score
+      value: 3.71
+      name: Score
+  - task:
+      type: text-generation
+    dataset:
+      name: Romanian_Academic_Benchmarks
+      type: Romanian_Academic_Benchmarks
+    metrics:
+    - type: accuracy
+      value: 50.56
+      name: Average accuracy
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_arc_challenge
+      type: OpenLLM-Ro/ro_arc_challenge
+    metrics:
+    - type: accuracy
+      value: 44.7
+      name: Average accuracy
+    - type: accuracy
+      value: 41.9
+      name: 0-shot
+    - type: accuracy
+      value: 44.3
+      name: 1-shot
+    - type: accuracy
+      value: 44.56
+      name: 3-shot
+    - type: accuracy
+      value: 45.5
+      name: 5-shot
+    - type: accuracy
+      value: 46.1
+      name: 10-shot
+    - type: accuracy
+      value: 45.84
+      name: 25-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_mmlu
+      type: OpenLLM-Ro/ro_mmlu
+    metrics:
+    - type: accuracy
+      value: 52.19
+      name: Average accuracy
+    - type: accuracy
+      value: 50.85
+      name: 0-shot
+    - type: accuracy
+      value: 51.24
+      name: 1-shot
+    - type: accuracy
+      value: 53.3
+      name: 3-shot
+    - type: accuracy
+      value: 53.39
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_winogrande
+      type: OpenLLM-Ro/ro_winogrande
+    metrics:
+    - type: accuracy
+      value: 67.23
+      name: Average accuracy
+    - type: accuracy
+      value: 65.19
+      name: 0-shot
+    - type: accuracy
+      value: 66.54
+      name: 1-shot
+    - type: accuracy
+      value: 67.88
+      name: 3-shot
+    - type: accuracy
+      value: 69.3
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_hellaswag
+      type: OpenLLM-Ro/ro_hellaswag
+    metrics:
+    - type: accuracy
+      value: 57.69
+      name: Average accuracy
+    - type: accuracy
+      value: 56.12
+      name: 0-shot
+    - type: accuracy
+      value: 57.37
+      name: 1-shot
+    - type: accuracy
+      value: 57.92
+      name: 3-shot
+    - type: accuracy
+      value: 58.18
+      name: 5-shot
+    - type: accuracy
+      value: 58.85
+      name: 10-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_gsm8k
+      type: OpenLLM-Ro/ro_gsm8k
+    metrics:
+    - type: accuracy
+      value: 30.23
+      name: Average accuracy
+    - type: accuracy
+      value: 29.42
+      name: 1-shot
+    - type: accuracy
+      value: 30.02
+      name: 3-shot
+    - type: accuracy
+      value: 31.24
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: OpenLLM-Ro/ro_truthfulqa
+      type: OpenLLM-Ro/ro_truthfulqa
+    metrics:
+    - type: accuracy
+      value: 51.34
+      name: Average accuracy
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary
+      type: LaRoSeDa_binary
+    metrics:
+    - type: macro-f1
+      value: 97.52
+      name: Average macro-f1
+    - type: macro-f1
+      value: 97.43
+      name: 0-shot
+    - type: macro-f1
+      value: 96.6
+      name: 1-shot
+    - type: macro-f1
+      value: 97.9
+      name: 3-shot
+    - type: macro-f1
+      value: 98.13
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass
+      type: LaRoSeDa_multiclass
+    metrics:
+    - type: macro-f1
+      value: 67.41
+      name: Average macro-f1
+    - type: macro-f1
+      value: 63.77
+      name: 0-shot
+    - type: macro-f1
+      value: 68.91
+      name: 1-shot
+    - type: macro-f1
+      value: 66.36
+      name: 3-shot
+    - type: macro-f1
+      value: 70.61
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_binary_finetuned
+      type: LaRoSeDa_binary_finetuned
+    metrics:
+    - type: macro-f1
+      value: 94.15
+      name: Average macro-f1
+  - task:
+      type: text-generation
+    dataset:
+      name: LaRoSeDa_multiclass_finetuned
+      type: LaRoSeDa_multiclass_finetuned
+    metrics:
+    - type: macro-f1
+      value: 87.13
+      name: Average macro-f1
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO
+      type: WMT_EN-RO
+    metrics:
+    - type: bleu
+      value: 24.01
+      name: Average bleu
+    - type: bleu
+      value: 6.92
+      name: 0-shot
+    - type: bleu
+      value: 29.33
+      name: 1-shot
+    - type: bleu
+      value: 29.79
+      name: 3-shot
+    - type: bleu
+      value: 30.02
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN
+      type: WMT_RO-EN
+    metrics:
+    - type: bleu
+      value: 27.36
+      name: Average bleu
+    - type: bleu
+      value: 4.5
+      name: 0-shot
+    - type: bleu
+      value: 30.3
+      name: 1-shot
+    - type: bleu
+      value: 36.96
+      name: 3-shot
+    - type: bleu
+      value: 37.7
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_EN-RO_finetuned
+      type: WMT_EN-RO_finetuned
+    metrics:
+    - type: bleu
+      value: 26.53
+      name: Average bleu
+  - task:
+      type: text-generation
+    dataset:
+      name: WMT_RO-EN_finetuned
+      type: WMT_RO-EN_finetuned
+    metrics:
+    - type: bleu
+      value: 40.36
+      name: Average bleu
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD
+      type: XQuAD
+    metrics:
+    - type: exact_match
+      value: 39.43
+      name: Average exact_match
+    - type: f1
+      value: 59.5
+      name: Average f1
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_finetuned
+      type: XQuAD_finetuned
+    metrics:
+    - type: exact_match
+      value: 44.45
+      name: Average exact_match
+    - type: f1
+      value: 59.76
+      name: Average f1
+  - task:
+      type: text-generation
+    dataset:
+      name: STS
+      type: STS
+    metrics:
+    - type: spearman
+      value: 77.2
+      name: Average spearman
+    - type: pearson
+      value: 77.87
+      name: Average pearson
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_finetuned
+      type: STS_finetuned
+    metrics:
+    - type: spearman
+      value: 85.8
+      name: Average spearman
+    - type: pearson
+      value: 86.05
+      name: Average pearson
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_EM
+      type: XQuAD_EM
+    metrics:
+    - type: exact_match
+      value: 4.45
+      name: 0-shot
+    - type: exact_match
+      value: 48.24
+      name: 1-shot
+    - type: exact_match
+      value: 52.03
+      name: 3-shot
+    - type: exact_match
+      value: 53.03
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: XQuAD_F1
+      type: XQuAD_F1
+    metrics:
+    - type: f1
+      value: 26.08
+      name: 0-shot
+    - type: f1
+      value: 68.4
+      name: 1-shot
+    - type: f1
+      value: 71.92
+      name: 3-shot
+    - type: f1
+      value: 71.6
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_Spearman
+      type: STS_Spearman
+    metrics:
+    - type: spearman
+      value: 77.76
+      name: 1-shot
+    - type: spearman
+      value: 76.72
+      name: 3-shot
+    - type: spearman
+      value: 77.12
+      name: 5-shot
+  - task:
+      type: text-generation
+    dataset:
+      name: STS_Pearson
+      type: STS_Pearson
+    metrics:
+    - type: pearson
+      value: 77.83
+      name: 1-shot
+    - type: pearson
+      value: 77.64
+      name: 3-shot
+    - type: pearson
+      value: 78.13
+      name: 5-shot
+---
+
+# vladciocan88/RoLlama3-8b-Instruct-2024-06-28-Q8_0-GGUF
+This model was converted to GGUF format from [`OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28`](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
+Refer to the [original model card](https://huggingface.co/OpenLLM-Ro/RoLlama3-8b-Instruct-2024-06-28) for more details on the model.
+
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+
+```bash
+brew install llama.cpp
+
+```
+Invoke the llama.cpp server or the CLI.
+
+### CLI:
+```bash
+llama-cli --hf-repo vladciocan88/RoLlama3-8b-Instruct-2024-06-28-Q8_0-GGUF --hf-file rollama3-8b-instruct-2024-06-28-q8_0.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo vladciocan88/RoLlama3-8b-Instruct-2024-06-28-Q8_0-GGUF --hf-file rollama3-8b-instruct-2024-06-28-q8_0.gguf -c 2048
+```
+
+Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+
+Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo vladciocan88/RoLlama3-8b-Instruct-2024-06-28-Q8_0-GGUF --hf-file rollama3-8b-instruct-2024-06-28-q8_0.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo vladciocan88/RoLlama3-8b-Instruct-2024-06-28-Q8_0-GGUF --hf-file rollama3-8b-instruct-2024-06-28-q8_0.gguf -c 2048
+```